{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T16:00:48Z","timestamp":1769270448129,"version":"3.49.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/wsc63780.2024.10838719","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:40:24Z","timestamp":1737398424000},"page":"1990-2001","source":"Crossref","is-referenced-by-count":1,"title":["Curriculum Interleaved Online Behavior Cloning for Complex Reinforcement Learning Applications"],"prefix":"10.1109","author":[{"given":"Michael","family":"M\u00f6bius","sequence":"first","affiliation":[{"name":"Operational Analysis and Studies, Airbus Defence and Space,Immenstaad,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Fischer","sequence":"additional","affiliation":[{"name":"Operational Analysis and Studies, Airbus Defence and Space,Immenstaad,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kallfass","sequence":"additional","affiliation":[{"name":"Simulations and Studies, Airbus Defence and Space,Immenstaad,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"G\u00f6ricke","sequence":"additional","affiliation":[{"name":"Army Concepts and Capabilities Development Centre,Bundeswehr,Bonn,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Doll","sequence":"additional","affiliation":[{"name":"Joint Support Service Command,Bundeswehr,Bonn,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"From the Game Map to the Battlefield \u2013 Using DeepMind\u2019s Advanced AlphaStar Techniques to Support Military Decision-Makers","volume-title":"NATO MSG-184: Towards Training and Decision Support for Complex Multi-Domain Operations, October 21st-22th","author":"Doll"},{"key":"ref2","article-title":"Reinforcement Learning from Imperfect Demonstrations","author":"Gao","year":"2018","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments","author":"Goecks","year":"2019","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5220\/0012312700003636"},{"issue":"1","key":"ref5","first-page":"3925","article-title":"Active Limitation Learning: Formal and Practical Reductions to IID Learning","volume":"15","author":"Judah","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","first-page":"3053","article-title":"RLlib: Abstractions for Distributed Reinforcement Learning","author":"Liang","year":"2018","journal-title":"International Conference on Machine Learning, July 10th-15th"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3575813.3595202"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/wsc57314.2022.10015234"},{"key":"ref9","article-title":"Natural Language AI for Military Decision Support and Swarm Control for Autonomous UAS Trained in a Combat Simulation","volume-title":"NATO MSG-207: Simulation: Going Beyond the Limitations of the Real World, October 19th-20th","author":"M\u00f6bius"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/wsc60868.2023.10408462"},{"issue":"181","key":"ref11","first-page":"1","article-title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","article-title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning","author":"Ross","year":"2014","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"627","article-title":"A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, April 11th-13th","author":"Ross"},{"key":"ref14","article-title":"Proximal Policy Optimization Algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852110"},{"key":"ref17","article-title":"Adaptive Behavior Cloning Regularization for Stable Offline-toOnline Reinforcement Learning","author":"Zhao","year":"2022","journal-title":"arXiv preprint"}],"event":{"name":"2024 Winter Simulation Conference (WSC)","location":"Orlando, FL, USA","start":{"date-parts":[[2024,12,15]]},"end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 Winter Simulation Conference (WSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10838618\/10838619\/10838719.pdf?arnumber=10838719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:34:00Z","timestamp":1737441240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10838719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/wsc63780.2024.10838719","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}